Approximation and estimation bounds for artificial neural networks

作者：Andrew R. Barron

摘要

For a common class of artificial neural networks, the mean integrated squared error between the estimated network and a target functionf is shown to be bounded by

论文关键词：Neural nets, approximation theory, estimation theory, complexity regularization, statistical risk

论文评审过程：

论文官网地址：https://doi.org/10.1007/BF00993164